{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T15:36:05Z","timestamp":1764776165412,"version":"3.46.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["18K15619"],"award-info":[{"award-number":["18K15619"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJSP2114"],"award-info":[{"award-number":["JPMJSP2114"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Med Biol Eng Comput"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:sec>\n                    <jats:title>Abstract<\/jats:title>\n                    <jats:p>Markerless tumor tracking in x-ray fluoroscopic images is an important technique for achieving precise dose delivery for moving lung tumors during radiation therapy. However, accurate tumor tracking is challenging due to the poor visibility of the target tumor overlapped by other organs such as rib bones. Dual-energy (DE) x-ray fluoroscopy can enhance tracking accuracy with improved tumor visibility by suppressing bones. However, DE x-ray imaging requires special hardware, limiting its clinical use. This study presents a deep learning-based DE subtraction (DES) synthesis method to avoid hardware limitations and enhance tracking accuracy. The proposed method employs a residual U-Net model trained on a simulated DES dataset from a digital phantom to synthesize DES from single-energy (SE) fluoroscopy. Experimental results using a digital phantom showed quantitative evaluation results of synthesis quality. Also, experimental results using clinical SE fluoroscopic images of ten lung cancer patients showed improved tumor tracking accuracy using synthesized DES images, reducing errors from 1.80 to 1.68 mm on average. The tracking success rate within a 25% movement range increased from 50.2% (SE) to 54.9% (DES). These findings indicate the feasibility of deep learning-based DES synthesis for markerless tumor tracking, offering a potential alternative to hardware-dependent DE imaging.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical abstract<\/jats:title>\n                    <jats:p>The U-Net model was first trained on simulated single-energy and dual-energy subtraction image pairs, then applied to synthesize DES from clinical X-ray images for improving tumor tracking<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11517-025-03432-9","type":"journal-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T09:20:25Z","timestamp":1756286425000},"page":"3857-3872","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning-based dual-energy subtraction synthesis from single-energy kV x-ray fluoroscopy for markerless tumor tracking"],"prefix":"10.1007","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8447-9079","authenticated-orcid":false,"given":"Jiaoyang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kei","family":"Ichiji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuwen","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshihiro","family":"Takai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noriyasu","family":"Homma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"issue":"4","key":"3432_CR1","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1001\/jamaoncol.2015.0735","volume":"1","author":"C Fitzmaurice","year":"2015","unstructured":"Fitzmaurice C, Dicker D, Pain A, Hamavid H, Moradi-Lakeh M, MacIntyre MF, Allen C, Hansen G, Woodbrook R, Wolfe C et al (2015) The global burden of cancer 2013. JAMA oncology 1(4):505\u2013527","journal-title":"JAMA oncology"},{"issue":"4","key":"3432_CR2","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1016\/S0360-3016(00)00748-3","volume":"48","author":"H Shirato","year":"2000","unstructured":"Shirato H, Shimizu S, Kunieda T, Kitamura K, Van Herk M, Kagei K, Nishioka T, Hashimoto S, Fujita K, Aoyama H et al (2000) Physical aspects of a real-time tumor-tracking system for gated radiotherapy. Int J Rad Oncol Bio Phys 48(4):1187\u20131195","journal-title":"Int J Rad Oncol Bio Phys"},{"issue":"3","key":"3432_CR3","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.radonc.2009.02.011","volume":"91","author":"J-B Pr\u00e9vost","year":"2009","unstructured":"Pr\u00e9vost J-B, Hoogeman MS, Praag J, Holt B, Levendag PC, Klaveren RJ, Pattynama P, Nuyttens JJ et al (2009) Stereotactic radiotherapy with real-time tumor tracking for non-small cell lung cancer: clinical outcome. Radiotherapy Oncol 91(3):296\u2013300","journal-title":"Radiotherapy Oncol"},{"issue":"2","key":"3432_CR4","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1148\/radiol.2291020499","volume":"229","author":"PR Geraghty","year":"2003","unstructured":"Geraghty PR, Kee ST, McFarlane G, Razavi MK, Sze DY, Dake MD (2003) CT-guided transthoracic needle aspiration biopsy of pulmonary nodules: needle size and pneumothorax rate. Radiology 229(2):475\u2013481. https:\/\/doi.org\/10.1148\/radiol.2291020499","journal-title":"Radiology"},{"issue":"5","key":"3432_CR5","doi-asserted-by":"publisher","first-page":"1442","DOI":"10.1016\/j.ijrobp.2005.04.024","volume":"63","author":"M Imura","year":"2005","unstructured":"Imura M, Yamazaki K, Shirato H, Onimaru R, Fujino M, Shimizu S, Harada T, Ogura S, Dosaka-Akita H, Miyasaka K, Nishimura M (2005) Insertion and fixation of fiducial markers for setup and tracking of lung tumors in radiotherapy. Int J Rad Oncol Bio Phys 63(5):1442\u20131447. https:\/\/doi.org\/10.1016\/j.ijrobp.2005.04.024","journal-title":"Int J Rad Oncol Bio Phys"},{"issue":"19","key":"3432_CR6","doi-asserted-by":"publisher","first-page":"4481","DOI":"10.1088\/0031-9155\/50\/19\/004","volume":"50","author":"RI Berbeco","year":"2005","unstructured":"Berbeco RI, Mostafavi H, Sharp GC, Jiang SB (2005) Towards fluoroscopic respiratory gating for lung tumours without radiopaque markers. Phys Med Bio 50(19):4481","journal-title":"Phys Med Bio"},{"key":"3432_CR7","doi-asserted-by":"crossref","unstructured":"Hazelaar C, Dahele M, Mostafavi H, Weide L, Slotman B, Verbakel W (2018) Markerless positional verification using template matching and triangulation of kV images acquired during irradiation for lung tumors treated in breath-hold. Phys Med Bio 63(11):115005","DOI":"10.1088\/1361-6560\/aac1a9"},{"issue":"18","key":"3432_CR8","doi-asserted-by":"publisher","first-page":"5585","DOI":"10.1088\/0031-9155\/55\/18\/021","volume":"55","author":"J Rottmann","year":"2010","unstructured":"Rottmann J, Aristophanous M, Chen A, Berbeco R et al (2010) A multi-region algorithm for markerless beam\u2019s-eye view lung tumor tracking. Phys Med Bio 55(18):5585","journal-title":"Phys Med Bio"},{"key":"3432_CR9","doi-asserted-by":"publisher","unstructured":"Ichiji K, Yoshida Y, Homma N, Zhang X, Bukovsky I, Takai Y, Yoshizawa M (2018) A key-point based real-time tracking of lung tumor in x-ray image sequence by using difference of gaussians filtering and optical flow. Phys Med Bio 63(18):185007. https:\/\/doi.org\/10.1088\/1361-6560\/aada71","DOI":"10.1088\/1361-6560\/aada71"},{"issue":"4","key":"3432_CR10","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1088\/0031-9155\/54\/4\/011","volume":"54","author":"T Lin","year":"2009","unstructured":"Lin T, Cervino LI, Tang X, Vasconcelos N, Jiang SB (2009) Fluoroscopic tumor tracking for image-guided lung cancer radiotherapy. Phys Med Bio 54(4):981","journal-title":"Phys Med Bio"},{"issue":"8","key":"3432_CR11","doi-asserted-by":"publisher","first-page":"3065","DOI":"10.1088\/1361-6560\/aa6393","volume":"62","author":"C-C Shieh","year":"2017","unstructured":"Shieh C-C, Caillet V, Dunbar M, Keall PJ, Booth JT, Hardcastle N, Haddad C, Eade T, Feain I (2017) A Bayesian approach for three-dimensional markerless tumor tracking using kV imaging during lung radiotherapy. Phys Med Bio 62(8):3065","journal-title":"Phys Med Bio"},{"issue":"1","key":"3432_CR12","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1053\/j.semradonc.2003.10.008","volume":"14","author":"H Shirato","year":"2004","unstructured":"Shirato H, Seppenwoolde Y, Kitamura K, Onimura R, Shimizu S (2004) Intrafractional tumor motion: lung and liver. Seminar Rad Oncol 14(1):10\u201318. https:\/\/doi.org\/10.1053\/j.semradonc.2003.10.008","journal-title":"Seminar Rad Oncol"},{"key":"3432_CR13","doi-asserted-by":"publisher","unstructured":"Bryant JH, Rottmann J, Lewis JH, Mishra P, Keall PJ, Berbeco RI (2014) Registration of clinical volumes to beams-eye-view images for real-time tracking. Med Phys 41(12):121703. https:\/\/doi.org\/10.1118\/1.4900603","DOI":"10.1118\/1.4900603"},{"issue":"1","key":"3432_CR14","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1118\/1.4903892","volume":"42","author":"R Patel","year":"2014","unstructured":"Patel R, Panfil J, Campana M, Block AM, Harkenrider MM, Surucu M, Roeske JC (2014) Markerless motion tracking of lung tumors using dual-energy fluoroscopy. Med Phys 42(1):254\u2013262. https:\/\/doi.org\/10.1118\/1.4903892","journal-title":"Med Phys"},{"issue":"12","key":"3432_CR15","doi-asserted-by":"publisher","first-page":"6987","DOI":"10.1118\/1.4935431","volume":"42","author":"MJ Menten","year":"2015","unstructured":"Menten MJ, Fast MF, Nill S, Oelfke U (2015) Using dual-energy x-ray imaging to enhance automated lung tumor tracking during real-time adaptive radiotherapy. Med Phys 42(12):6987\u20136998. https:\/\/doi.org\/10.1118\/1.4935431","journal-title":"Med Phys"},{"issue":"7","key":"3432_CR16","doi-asserted-by":"publisher","first-page":"3235","DOI":"10.1002\/mp.13573","volume":"46","author":"M Haytmyradov","year":"2019","unstructured":"Haytmyradov M, Mostafavi H, Wang A, Zhu L, Surucu M, Patel R, Ganguly A, Richmond M, Cassetta R, Harkenrider MM, Roeske JC (2019) Markerless tumor tracking using fast-kV switching dual-energy fluoroscopy on a benchtop system. Med Phys 46(7):3235\u20133244. https:\/\/doi.org\/10.1002\/mp.13573","journal-title":"Med Phys"},{"issue":"8","key":"3432_CR17","doi-asserted-by":"publisher","first-page":"3332","DOI":"10.1002\/mp.14211","volume":"47","author":"L Shi","year":"2020","unstructured":"Shi L, Lu M, Bennett NR, Shapiro E, Zhang J, Colbeth R, Star-Lack J, Wang AS (2020) Characterization and potential applications of a dual-layer flat-panel detector. Med Phys 47(8):3332\u20133343","journal-title":"Med Phys"},{"key":"3432_CR18","doi-asserted-by":"publisher","unstructured":"Kaur M, Wagstaff P, Mostafavi H, Lehmann M, Morf D, Zhu L, Kang H, Walczak M, Harkenrider MM, Roeske JC (2022) Effect of different noise reduction techniques and template matching parameters on markerless tumor tracking using dual-energy imaging. J Appl Clinic Med Phys 23(12). https:\/\/doi.org\/10.1002\/acm2.13821","DOI":"10.1002\/acm2.13821"},{"issue":"11","key":"3432_CR19","doi-asserted-by":"publisher","first-page":"4916","DOI":"10.1002\/mp.13175","volume":"45","author":"DC Hansen","year":"2018","unstructured":"Hansen DC, Landry G, Kamp F, Li M, Belka C, Parodi K, Kurz C (2018) Scatternet: a convolutional neural network for cone-beam CT intensity correction. Medical Phys 45(11):4916\u20134926","journal-title":"Medical Phys"},{"key":"3432_CR20","doi-asserted-by":"publisher","first-page":"78031","DOI":"10.1109\/ACCESS.2018.2884704","volume":"6","author":"S Xie","year":"2018","unstructured":"Xie S, Yang C, Zhang Z, Li H (2018) Scatter artifacts removal using learning-based method for CBCT in IGRT system. IEEE Access 6:78031\u201378037","journal-title":"IEEE Access"},{"key":"3432_CR21","doi-asserted-by":"publisher","unstructured":"Lee D, Kim H, Choi B, Kim H-J (2019) Development of a deep neural network for generating synthetic dual-energy chest x-ray images with single x-ray exposure. Phys Med Bio 64(11):115017. https:\/\/doi.org\/10.1088\/1361-6560\/ab1cee","DOI":"10.1088\/1361-6560\/ab1cee"},{"issue":"3","key":"3432_CR22","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.ijrobp.2020.07.2154","volume":"108","author":"W Zhao","year":"2020","unstructured":"Zhao W, Lv T, Chen Y, Xing L (2020) Dual-energy CT imaging using a single-energy CT data via deep learning: a contrast-enhanced CT study. Int J Rad Oncol Bio Phys 108(3):43. https:\/\/doi.org\/10.1016\/j.ijrobp.2020.07.2154","journal-title":"Int J Rad Oncol Bio Phys"},{"issue":"12","key":"3432_CR23","doi-asserted-by":"publisher","first-page":"7590","DOI":"10.1002\/mp.15295","volume":"48","author":"X He","year":"2021","unstructured":"He X, Cai W, Li F, Fan Q, Zhang P, Cuaron JJ, Cervi\u00f1o LI, Li X, Li T (2021) Decompose kV projection using neural network for improved motion tracking in paraspinal SBRT. Medical Phys 48(12):7590\u20137601. https:\/\/doi.org\/10.1002\/mp.15295","journal-title":"Medical Phys"},{"issue":"9","key":"3432_CR24","doi-asserted-by":"publisher","first-page":"4902","DOI":"10.1118\/1.3480985","volume":"37","author":"WP Segars","year":"2010","unstructured":"Segars WP, Sturgeon G, Mendonca S, Grimes J, Tsui BMW (2010) 4d XCAT phantom for multimodality imaging research. Medical Phys 37(9):4902\u20134915. https:\/\/doi.org\/10.1118\/1.3480985","journal-title":"Medical Phys"},{"issue":"3","key":"3432_CR25","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1118\/1.594957","volume":"8","author":"WR Brody","year":"1981","unstructured":"Brody WR, Butt G, Hall A, Macovski A (1981) A method for selective tissue and bone visualization using dual energy scanned projection radiography. Medical Phys 8(3):353\u2013357. https:\/\/doi.org\/10.1118\/1.594957","journal-title":"Medical Phys"},{"key":"3432_CR26","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, 5-9 October, 2015, Proceedings, Part III 18, pp 234\u2013241. Springer","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3432_CR27","first-page":"13","volume":"8","author":"M McCormick","year":"2014","unstructured":"McCormick M, Liu X, Jomier J, Marion C, Ibanez L (2014) ITK: enabling reproducible research and open science. Frontier Neuroinf 8:13","journal-title":"Frontier Neuroinf"},{"key":"3432_CR28","unstructured":"Gonzalez RC, Woods RE (2002) Digital image processing. upper saddle river. J.: Prentice Hall"},{"key":"3432_CR29","unstructured":"Chollet F, et al. Keras. https:\/\/github.com\/fchollet\/keras"},{"key":"3432_CR30","doi-asserted-by":"crossref","unstructured":"Segars W, Bond J, Frush J, Hon S, Eckersley C, Williams CH, Feng J, Tward DJ, Ratnanather J, Miller M et al (2013) Population of anatomically variable 4D XCAT adult phantoms for imaging research and optimization. Medical Phys 40(4):043701","DOI":"10.1118\/1.4794178"},{"key":"3432_CR31","doi-asserted-by":"crossref","unstructured":"Unberath M, Zaech J-N, Lee SC, Bier B, Fotouhi J, Armand M, Navab N (2018) DeepDRR\u2013a catalyst for machine learning in fluoroscopy-guided procedures. In: International Conference on Medical Image Computing and Computer-assisted Intervention, pp 98\u2013106. Springer","DOI":"10.1007\/978-3-030-00937-3_12"},{"issue":"8","key":"3432_CR32","doi-asserted-by":"publisher","first-page":"4448","DOI":"10.1002\/mp.15007","volume":"48","author":"J O\u2019Connell","year":"2021","unstructured":"O\u2019Connell J, Bazalova-Carter M (2021) fastCAT: fast cone beam CT (CBCT) simulation. Medical Phys 48(8):4448\u20134458","journal-title":"Medical Phys"}],"container-title":["Medical &amp; Biological Engineering &amp; Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11517-025-03432-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11517-025-03432-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11517-025-03432-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T15:32:17Z","timestamp":1764775937000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11517-025-03432-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":32,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["3432"],"URL":"https:\/\/doi.org\/10.1007\/s11517-025-03432-9","relation":{},"ISSN":["0140-0118","1741-0444"],"issn-type":[{"type":"print","value":"0140-0118"},{"type":"electronic","value":"1741-0444"}],"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"13 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The artificial data are not publicly available since they were generated using licensed software, and the clinical data cannot be publicly shared from the authors for privacy reasons.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"This manuscript has not been published or presented elsewhere, in whole or in part, and is not under consideration by another journal. All authors have read and understood the journal\u2019s policies and confirm compliance.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}